FedGDC-P: Communication-efficient Personalized Graph Federated Learning Based On Dataset Condensation

In the era of Big Data, graph data is often collected from dispersed addresses and stored separately, making our research on this data subject to transmission and privacy constraints. So we often introduce federated learning, a novel distributed machine learning algorithm, in our studies of graph data. However, the application of federated learning in the field of graph data research is constrained by issues such as the surge in communication costs and the decrease in model accuracy caused by data heterogeneity. To address both the communication stress problem and the accuracy impairment caused by heterogeneity in graph federated learning, we propose a communication-efficient personalized federated learning algorithm, named FedGDC-P. In this algorithm, we introduce the dataset condensation technique in the global information collection process to transfer the features of local data with a one-time transmission of the distilled data instead of multiple transmissions of the model parameters, helping the model on the server to build a panorama of data distribution in order to reduce the amount of communication data during the training process. Subsequently, we execute the obtained model locally to personalize the training process to improve the adaptation of the model to personalized local data in order to enhance the overall training effect. The experiments demonstrate that our algorithm can achieve or even outperform SOTA with only 5% communication budget.